Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add flonat/flonat-research --skill grill-megit clone --depth 1 https://github.com/flonat/flonat-researchWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/flonat/flonat-research/grill-me)<a href="https://agentmods.dev/skills/flonat/flonat-research/grill-me"><img src="https://agentmods.dev/badge/skills/flonat/flonat-research/grill-me/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/flonat/flonat-research/grill-me"><img src="https://agentmods.dev/badge/skills/flonat/flonat-research/grill-me.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00079 | $0.02817 |
| Opus 5 | $0.00039 | $0.01409 |
| Sonnet 5 | $0.00016 | $0.00563 |
| Haiku 4.5 | $0.00008 | $0.00282 |
Grade A, and why
grill-me scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Grill Me — Interactive Oral-Exam Drill
You answer, out loud, one grounded question at a time. This skill plays a skeptical examiner and interrogates you — escalating on weak or evasive answers — then hands you a study sheet of what you fumbled, with model answers. Two flavours: defend your own research, or study a class you're learning.
Two Modes (auto-detected; override with --defend / --study)
| Defend | Study | |
|---|---|---|
| Target | Your own paper / model / proof / research idea | A class, subject, textbook chapter, lecture notes you're learning |
| Goal | Rehearse defending your choices under pressure | Test + deepen recall and understanding of the material |
| "Right answer"? | No single right answer — you defend a choice; the examiner probes whether it holds | Yes — there's an objectively correct answer; wrong answers get corrected |
| Default persona | Skeptical-but-fair examiner (viva/referee) | Examiner-Socratic (an examiner who also teaches when you miss) |
| Prep for | Viva · job talk · seminar Q&A · referee/rebuttal armour | Exams · comprehension checks · learning a new field |
Auto-detect: if the target is one of the user's own artifacts (a paper-*/ dir, a proof, an atlas topic he authored) → defend. If it's course material / textbook / lecture notes / a subject he's revising → study. When ambiguous, ask once.
Everything below is shared; mode-specific differences are called out inline.
When to Use
- Defend: preparing for a viva / thesis defense / job talk / seminar Q&A; building referee/rebuttal armour before submission.
- Study: revising for an exam; checking you actually understand a class, textbook chapter, or a new field — active-recall practice, not passive re-reading.
When NOT to Use
- You want a written critique of a paper, not a live drill →
referee2-reviewer/paper-critic/review-cluster. - You want to stress-test an argument in prose →
devils-advocate. - You want to draft a rebuttal to genuine venue reviews you already have →
review-response/strategic-revision --external. - You want a passive summary of the material → just ask for one; grill-me is for being tested.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 6d ago First seen · 146 lines · 79 tokens per session scan A 63677dc9e059
grill-me is a skill published in the GitHub repository flonat/flonat-research (132 stars, last pushed 15d ago), licensed MIT. It adds 79 tokens to every session and 2,817 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
html-ppt-zhangzara-vellum
A humanities lecture: how Renaissance linear perspective reshaped early cartography — sources, argument, and evidence. Built as a decision-grade academic research deck for faculty, graduate seminar.
eq-emotional-intelligence
An emotional-intelligence coaching aid based on models that describe recognizing, understanding, and managing emotions. It covers self-awareness, self-management, awareness of others, and relationship skills.
tipkit-generator
Generate TipKit infrastructure with inline/popover tips, rules, display frequency, and testing utilities. Use when adding contextual tips or feature discovery to an iOS/macOS app.
course-material-creator
Create custom educational materials including syllabi, lesson plans, assessments, reading lists, and learning objectives. Use when building course curricula, training programs, workshops, or educational content.
github-contributor
Find suitable open-source contribution opportunities and prepare focused GitHub pull requests with project-specific validation and review context.
education-data-source-edfacts
EDFacts — K-12 outcomes: assessment proficiency, ACGR graduation rates, ESSA accountability at school/district level (2009-2020). Within-state trends and subgroup gaps. Complements CCD with outcome data. Cannot compare across states — use NAEP.